A personal OS layer for iOS.

Why I built it

Every notes app, reminder app, and capture tool I tried had the same problem: it stored what I said, not what I meant. I wanted something that understood context — is this a task? a thought? something I need to act on tonight or next month? I couldn't find it so I built it.

What it is

SYNTH captures raw inputs throughout the day — notes, thoughts, tasks — classifies them via LLM, and routes them intelligently. Built in Swift. Classification runs on-device and via API with tiered model routing depending on complexity. The on-device path keeps it fast. The API path handles the hard cases.

Behavioral intelligence, quietly running in the background.

Why I built it

I noticed I kept repeating the same mistakes — not big ones, small ones. Patterns I couldn't see because I was too close to them. I wanted something that watched over time and surfaced those patterns without me having to go looking. Not a journal. Not a mood tracker. Something quieter.

What it is

sarvis turns unstructured daily captures into behavioral signals over time. The core pipeline — capture → LLM structuring → pattern extraction — is working. Still early. The hard part isn't the engineering, it's figuring out what a useful 'pattern' actually is.

A PM brain for any git repo.

Why I built it

Every time I started a new session with an AI coding assistant, I'd spend the first 10 minutes re-explaining the project. What it does, how it's structured, what's already been tried. That's wasted time every single session. I wanted the assistant to already know. So I made a way for it to know.

What it is

cortex is a Claude Code skill I built and open-sourced. It installs a post-commit hook that automatically scans your repo and updates a private context file after every push. Any AI assistant you bring into the project picks it up immediately. No re-explaining.

GitHub →